{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S43XC3NHGAJTX62WDAXWUSNEP6","short_pith_number":"pith:S43XC3NH","schema_version":"1.0","canonical_sha256":"9737716da730133bfb56182f6a49a47f879f0c2597e8ab6ab9f456f2b4063a02","source":{"kind":"arxiv","id":"2406.08659","version":1},"attestation_state":"computed","paper":{"title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Biao Zhang, Bing Li, Cheng Zheng, Jinjie Mai, Peter Wonka, Wenxuan Zhu","submitted_at":"2024-06-12T21:44:04Z","abstract_excerpt":"While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. To this end, we propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text. Specifically, we factor the T2MVid problem into viewpoint-space and time components. Such factorization allows"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.08659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T21:44:04Z","cross_cats_sorted":[],"title_canon_sha256":"7dd4d50d25dc3052fac13e36a107e996e581dd55509a765ab70540ac20452d6c","abstract_canon_sha256":"f0d390f56d5523bd5c27d790f9c098e6da17321c581cdbb8aab70ef2d52064d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:20.925732Z","signature_b64":"1OksGstKEyLJ4ooOf4tpXhgYc0WGLeVSpC5xT7zr3Y4xnu4CDLb+SBwKur6Nk2zgBxgwXOBHKQThX685JhW7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9737716da730133bfb56182f6a49a47f879f0c2597e8ab6ab9f456f2b4063a02","last_reissued_at":"2026-07-05T08:31:20.925230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:20.925230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Biao Zhang, Bing Li, Cheng Zheng, Jinjie Mai, Peter Wonka, Wenxuan Zhu","submitted_at":"2024-06-12T21:44:04Z","abstract_excerpt":"While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. To this end, we propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text. Specifically, we factor the T2MVid problem into viewpoint-space and time components. Such factorization allows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08659","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.08659/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.08659","created_at":"2026-07-05T08:31:20.925287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08659v1","created_at":"2026-07-05T08:31:20.925287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08659","created_at":"2026-07-05T08:31:20.925287+00:00"},{"alias_kind":"pith_short_12","alias_value":"S43XC3NHGAJT","created_at":"2026-07-05T08:31:20.925287+00:00"},{"alias_kind":"pith_short_16","alias_value":"S43XC3NHGAJTX62W","created_at":"2026-07-05T08:31:20.925287+00:00"},{"alias_kind":"pith_short_8","alias_value":"S43XC3NH","created_at":"2026-07-05T08:31:20.925287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01722","citing_title":"AR4D: Autoregressive 4D Generation from Monocular Videos","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6","json":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6.json","graph_json":"https://pith.science/api/pith-number/S43XC3NHGAJTX62WDAXWUSNEP6/graph.json","events_json":"https://pith.science/api/pith-number/S43XC3NHGAJTX62WDAXWUSNEP6/events.json","paper":"https://pith.science/paper/S43XC3NH"},"agent_actions":{"view_html":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6","download_json":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6.json","view_paper":"https://pith.science/paper/S43XC3NH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08659&json=true","fetch_graph":"https://pith.science/api/pith-number/S43XC3NHGAJTX62WDAXWUSNEP6/graph.json","fetch_events":"https://pith.science/api/pith-number/S43XC3NHGAJTX62WDAXWUSNEP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6/action/storage_attestation","attest_author":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6/action/author_attestation","sign_citation":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6/action/citation_signature","submit_replication":"https://pith.science/pith/S43XC3NHGAJTX62WDAXWUSNEP6/action/replication_record"}},"created_at":"2026-07-05T08:31:20.925287+00:00","updated_at":"2026-07-05T08:31:20.925287+00:00"}